applsci-logo

Journal Browser

Journal Browser

Computer Vision and Deep Learning for Activity Recognition

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 31 October 2025 | Viewed by 121

Special Issue Editors

School of Electronic Science and Engineering, Nanjing University, Nanjing 210023, China
Interests: visual depth perception; 3D reconstruction; bio-image informatics
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
School of Control Science and Engineering, Shandong University, Jinan 250061, China
Interests: intelligent coding and processing of immersive media (point cloud, light field); computer vision; dash-based video (especially 360° panoramic video) streaming media transmission control
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Human activity recognition (HAR) has gained significant attention due to its wide-ranging applications in healthcare, smart surveillance, human-computer interaction, and autonomous systems. Despite significant progress, challenges such as data scarcity, model generalization, and privacy concerns remain critical barriers to real-world deployment. This Special Issue aims to explore recent advancements in computer vision and deep learning techniques for robust, efficient, and privacy-preserving activity recognition.

Deep learning models, particularly convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformer-based architectures, and graph neural networks (GNNs), have revolutionized HAR by enabling automatic feature extraction and enhanced spatiotemporal pattern recognition. The integration of multimodal data sources, including RGB-D cameras, LiDAR, wearable sensors, and thermal imaging, further enhances the accuracy and adaptability of activity recognition systems. However, challenges such as modality misalignment, missing modalities, and heterogeneous data integration remain open research problems.

This Special Issue invites contributions that address key challenges in HAR, such as real-time processing, occlusion handling, domain adaptation, generalization across diverse environments, and privacy-preserving learning. Topics of interest include, but are not limited to, the following:

  • Novel deep learning architectures for activity recognition;
  • Self-supervised, few-shot, and federated learning approaches;
  • Multimodal fusion techniques for enhanced recognition;
  • Explainability and interpretability in deep HAR models;
  • Real-time and low-power implementations for edge AI;
  • Synthetic data generation and augmentation using generative AI (e.g., diffusion models);
  • Human–object interaction modeling and scene understanding;
  • Privacy-preserving techniques and federated learning for HAR;
  • Applications in healthcare, assistive technologies, surveillance, and emerging fields, such as the metaverse and virtual reality.

We encourage original research articles, review papers, and case studies showcasing innovative methodologies and real-world implementations of computer vision and deep learning in activity recognition. This Special Issue aims to advance the field by fostering interdisciplinary collaborations and discussions on emerging trends, novel solutions, and future directions in HAR.

Dr. Yang Li
Prof. Dr. Hui Yuan
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • human activity recognition
  • deep learning
  • computer vision
  • multimodal fusion
  • edge AI
  • privacy-preserving learning
  • self-supervised learning
  • federated learning
  • generative AI
  • explainable AI

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

23 pages, 2120 KiB  
Article
A Meta-Learning-Based Recognition Method for Multidimensional Feature Extraction and Fusion of Underwater Targets
by Xiaochun Liu, Yunchuan Yang, Youfeng Hu, Xiangfeng Yang, Liwen Liu, Lei Shi and Jianguo Liu
Appl. Sci. 2025, 15(10), 5744; https://doi.org/10.3390/app15105744 - 21 May 2025
Abstract
To tackle the challenges of relative attitude adaptability and limited sample availability in underwater moving target recognition for active sonar, this study focuses on key aspects such as feature extraction, network model design, and information fusion. A pseudo-three-dimensional spatial feature extraction method is [...] Read more.
To tackle the challenges of relative attitude adaptability and limited sample availability in underwater moving target recognition for active sonar, this study focuses on key aspects such as feature extraction, network model design, and information fusion. A pseudo-three-dimensional spatial feature extraction method is proposed by integrating generalized MUSIC with range–dimension information. The pseudo-WVD time–frequency feature is enhanced through the incorporation of prior knowledge. Additionally, the Doppler frequency shift distribution feature for underwater moving targets is derived and extracted. A multidimensional feature information fusion network model based on meta-learning is developed. Meta-knowledge is extracted separately from spatial, time–frequency, and Doppler feature spectra, to improve the generalization capability of single-feature task networks during small-sample training. Multidimensional feature information fusion is achieved via a feature fusion classifier. Finally, a sample library is constructed using simulation-enhanced data and experimental data for network training and testing. The results demonstrate that, in the few-sample scenario, the proposed method leverages the complementary nature of multidimensional features, effectively addressing the challenge of limited adaptability to relative horizontal orientation angles in target recognition, and achieving a recognition accuracy of up to 97.1%. Full article
(This article belongs to the Special Issue Computer Vision and Deep Learning for Activity Recognition)
Show Figures

Figure 1

Back to TopTop